Research map / Vision-language and multimodal / Robot action and navigation
ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Add progress and sub-goal prediction losses | Seq2Seq on ALFRED · ALFRED test seen | Task success: 2.1 -> 4.0 | Helped |
| Add progress and sub-goal prediction losses | Seq2Seq on ALFRED · ALFRED test unseen | Task success: 0.5 -> 0.4 | Hurt |
| Add progress and sub-goal prediction losses | Seq2Seq on ALFRED · ALFRED test seen | Goal-condition success: 7.4 -> 9.4 | Helped |
| Add progress and sub-goal prediction losses | Seq2Seq on ALFRED · ALFRED test unseen | Goal-condition success: 7.1 -> 7.0 | Hurt |
| Add progress and sub-goal prediction losses | Seq2Seq on ALFRED · ALFRED validation seen | Path-weighted sub-goal success (average): 67 -> 68 | Helped |
| Add progress and sub-goal prediction losses | Seq2Seq on ALFRED · ALFRED validation unseen | Path-weighted sub-goal success (average): 45 -> 46 | Helped |
| Use only low-level instructions, without the high-level goal (ablation) | Seq2Seq on ALFRED · ALFRED test seen | Task success: 2.1 -> 2.7 | Helped |
| Use only low-level instructions, without the high-level goal (ablation) | Seq2Seq on ALFRED · ALFRED test unseen | Task success: 0.5 -> 0.5 | No clear effect |
| Remove language input (ablation) | Seq2Seq on ALFRED · ALFRED test seen | Task success: 2.1 -> 0.2 | Hurt |
| Remove visual input (ablation) | Seq2Seq on ALFRED · ALFRED test seen | Task success: 2.1 -> 0.0 | Hurt |
| Use only the high-level goal, without step-by-step instructions (ablation) | Seq2Seq on ALFRED · ALFRED validation seen | Task success: 2.4 -> 0.1 | Hurt |
| Add only the progress prediction loss (ablation) | Seq2Seq on ALFRED · ALFRED validation seen | Task success: 2.4 -> 2.1 | No clear effect |
Closest papers by meaning
- EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents (ICML 2025 · similarity 0.89)
- Not All Features Are Created Equal: A Mechanistic Study of Vision-Language-Action Models (NeurIPS 2026 · similarity 0.88)
- FineVLA: Fine-Grained Instruction Alignment for Steerable Vision-Language-Action Policies (NeurIPS 2026 · similarity 0.88)
- Provable Ordering and Continuity in Vision-Language Pretraining for Generalizable Embodied Agents (NeurIPS 2025 · similarity 0.88)
- ROVER: Recursive Reasoning Over Videos with Vision-Language Models for Embodied Tasks (NeurIPS 2025 · similarity 0.87)
- NavBench: Probing Multimodal Large Language Models for Embodied Navigation (NeurIPS 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.